Supervisor:
Southwest Ordnance Industry Bureau
Organizer:
Chongqing Ordnance Industry Society
Chongqing University of Technology
Chongqing University of Technology
Active stereo vision matching algorithm based on four color structured light line pattern
| DOI: | 10.11809/bqzbgcxb2024.11.040 |
| Keywords: | active stereo vision; three dimensional reconstruction; structured light; line pattern; stereo matching |
| Abstract: | Active stereo vision is one of the most effective ways to obtain 3D information of objects.Currently, it is still very difficult to reconstruct 3D shape of a dynamic object in real time.A promising solution to deal with this problem is to design the structured light pattern with wide applicability and to develop the stereo vision matching algorithm with high accuracy.A novel structured light line pattern that composed of red, light green, cyan, purple four color lines(FCL) and the stereo vision matching algorithm according to the designed pattern are proposed for this purpose.The lines in different color in the both camera views are extracted in the Hue Saturation Value(HSV) color space based on slope difference distribution(SDD) threshold selection.After center alignment, the cyan lines in two camera views are matched based on a line indexing algorithm.Then, the light green lines and the purple lines are matched based on the matched cyan lines respectively.Finally, the red lines are matched based on the matched cyan, light green and purple lines.The measurement error of the proposed method for the grid is 0.3825mm, the measurement results of different methods for the grid showed that the measurement accuracy of the proposed method is superior to other measurement methods.In addition, the reconstruction results of the different experiment objects showed that the proposed method is more robust in reconstructing the static objects and dynamic objects. |
| Published: | 2024-11-30 |